sentiment_analysis.yaml

_type: prompt
input_types: {}
input_variables:
  - conversation
  - sentiments
  - format_instructions
name: null
output_parser: null
partial_variables: {}
template: |
          <|begin_of_text|><|start_header_id|>system<|end_header_id|>
          Classify the overall customer's mood throughout the call in only one of the sentiments in the list
          {format_instructions}

          <|eot_id|><|start_header_id|>user<|end_header_id|>
          Input conversation:
          I had to compare two versions of Hamlet for my Shakespeare class and unfortunately I picked this version…
          sentiment list: ['positive', 'neutral', 'negative']
          <|eot_id|><|start_header_id|>assistant<|end_header_id|>negative
          <|eot_id|><|start_header_id|>user<|end_header_id|>
          Input conversation: 
          This Charles outing is pretty good, I felt it is a pretty good-key performance…
          sentiment list: ['positive', 'neutral', 'negative']
          <|eot_id|><|start_header_id|>assistant<|end_header_id|>positive
          <|eot_id|><|start_header_id|>user<|end_header_id|>
          input conversation: 
          My family has watched Arthur Bach stumble and stammer since the movie first came out. We have most lines memorized…
          sentiment list: ['exited', 'neutral', 'disappointed']
          <|eot_id|><|start_header_id|>assistant<|end_header_id|>exited
          <|eot_id|><|start_header_id|>user<|end_header_id|>
          input conversation:
          {conversation}
          sentiment list: {sentiments}
          <|eot_id|><|start_header_id|>assistant<|end_header_id|>
          
template_format: f-string
validate_template: false